Divyansh Kaushik
7 papers · 2018–2022 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (17) 🐣 Hot Topic Early Bird 🔥 Unstoppable · Bronze
❓
The Questioner
Top co-authors
Research topics
Keywords
spurious correlation
(3)
counterfactual augmentation
(2)
out-of-domain evaluation
(2)
sentiment analysis
(2)
question answering
(2)
causal inference
(2)
domain adaptation
(1)
model robustness
(1)
dataset creation
(1)
natural language inference
(1)
reading comprehension
(1)
feature attribution
(1)
distribution shift
(1)
label shift
(1)
distribution alignment
(1)
feature feedback
(1)
counterfactual data augmentation
(1)
model assessment
(1)
adversarial data collection
(1)
baseline model
(1)
Papers
Practical Benefits of Feature Feedback Under Distribution Shift
EMNLP 2022
Dynabench: Rethinking Benchmarking in NLP
NAACL 2021
Explaining the Efficacy of Counterfactually Augmented Data
ICLR 2021
On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study
ACL 2021
Learning The Difference That Makes A Difference With Counterfactually-Augmented Data
ICLR 2020
Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment
ICML 2019
How Much Reading Does Reading Comprehension Require? A Critical Investigation of Popular Benchmarks
EMNLP 2018